Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names followed by punctuation or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     camber
    0.19
     geändert
    0.19
    फ्टी
    0.18
     Allemagne
    0.18
     usamos
    0.18
     resumen
    0.17
    cribing
    0.17
     alrededores
    0.17
     stupe
    0.17
     conclusão
    0.17
    POSITIVE LOGITS
    ,
    0.22
    .
    0.21
    ،
    0.21
     and
    0.20
    ?
    0.19
    :
    0.19
     और
    0.19
    !
    0.18
    ，
    0.18
     যিনি
    0.18
    Act Density 0.094%

    No Known Activations